publications
publications by categories in reversed chronological order. generated by jekyll-scholar.
2026
- WorldRFT: Latent world model planning with reinforcement fine-tuning for autonomous driving2026Proceedings of the AAAI Conference on Artificial Intelligence 40 (14), 11649… [10](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=10655084415478563555
- Unifying Language-Action Understanding and Generation for Autonomous Driving2026arXiv preprint arXiv:2603.01441 [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- StreetForward: Perceiving Dynamic Street with Feedforward Causal Attention2026arXiv preprint arXiv:2603.19552 [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- StreamingClaw Technical Report2026arXiv preprint arXiv:2603.22120 [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- Planagent: A multi-modal large language agent for closed-loop vehicle motion planning2026IEEE Transactions on Cognitive and Developmental Systems [55](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=4421753326440065257
- Method and apparatus for generating trajectory, electronic device, storage medium2026US Patent App. 19/037,583 [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs2026arXiv preprint arXiv:2602.10377 [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- FAAR: Format-Aware Adaptive Rounding for NVFP42026arXiv preprint arXiv:2603.22370 [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoning2026arXiv preprint arXiv:2602.01983 [4](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=7889678616000217910
- Evaluating the Search Agent in a Parallel World2026arXiv preprint arXiv:2603.04751 [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- DriveCombo: Benchmarking Compositional Traffic Rule Reasoning in Autonomous Driving2026arXiv preprint arXiv:2603.01637 [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- Correctad: A self-correcting agentic system to improve end-to-end planning in autonomous driving2026Proceedings of the AAAI Conference on Artificial Intelligence 40 (10), 7755-7763 [1](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=9391779730238116875
2025
- Transdiffuser: End-to-end trajectory generation with decorrelated multi-modal representation for autonomous driving2025arXiv e-prints, arXiv: 2505.09315 [21](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=7007766532717179773
- Transdiffuser: Diverse trajectory generation with decorrelated multi-modal representation for end-to-end autonomous driving2025arXiv preprint arXiv:2505.09315 [3](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=12624178323067622969
- The better you learn, the smarter you prune: Towards efficient vision-language-action models via differentiable token pruning2025arXiv preprint arXiv:2509.12594 [22](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=9527737081615138439
- StyledStreets: Multi-style Street Simulator with Spatial and Temporal Consistency2025arXiv preprint arXiv:2503.21104 [1](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=36853680135788572
- Streetcrafter: Street view synthesis with controllable video diffusion models2025Proceedings of the Computer Vision and Pattern Recognition Conference, 822-832 [43](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=10025705900330225678
- Street Gaussians: Modeling Dynamic Urban Scenes With Gaussian Primitives2025IEEE transactions on pattern analysis and machine intelligence [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model2025arXiv preprint arXiv:2511.22039 [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- Recondreamer: Crafting world models for driving scene reconstruction via online restoration2025Proceedings of the Computer Vision and Pattern Recognition Conference, 1559-1569 [86](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=10376473717473330982
- PosePilot: Steering camera pose for generative world models with self-supervised depth2025IEEE/RSJ International Conference on Intelligent Robots and Systems… [4](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=10498075774223536829
- Learning Personalized Driving Styles via Reinforcement Learning from Human Feedback2025arXiv preprint arXiv:2503.10434 [3](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=8047799359356458182
- HiNeuS: High-fidelity Neural Surface Mitigating Low-texture and Reflective Ambiguity2025Proceedings of the IEEE/CVF International Conference on Computer Vision… [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- Hierarchy UGP: Hierarchy Unified Gaussian Primitive for Large-Scale Dynamic Scene Reconstruction2025Proceedings of the IEEE/CVF International Conference on Computer Vision… [](http://scholar.google.com/citations?user=1J061HIAAAAJ&hl=en&cstart=0&pagesize=100&sortby=pubdate
- Geodrive: 3d geometry-informed driving world model with precise action control2025arXiv preprint arXiv:2505.22421 [15](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=15666192644711815204
- Generalizing motion planners with mixture of experts for autonomous driving2025IEEE International Conference on Robotics and Automation (ICRA), 6033-6039 [23](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=8525832948576027576
-
Finetuning generative trajectory model with reinforcement learning from human feedback2025arXiv e-prints, arXiv: 2503.10434 [31](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=14639323362602446741 - Drivingsphere: Building a high-fidelity 4d world for closed-loop simulation2025Proceedings of the Computer Vision and Pattern Recognition Conference, 27531… [32](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=1178226343426138884
- DriveAgent-R1: Advancing VLM-based autonomous driving with hybrid thinking and active perception2025arXiv e-prints, arXiv: 2507.20879 [9](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=13273096394978228899
- DriveAgent-R1: Advancing VLM-based Autonomous Driving with Active Perception and Hybrid Thinking2025arXiv preprint arXiv:2507.20879 [3](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=5635847788066915044,17179949796365284237
- Dive: Efficient multi-view driving scenes generation based on video diffusion transformer2025arXiv preprint arXiv:2504.19614 [6](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=17699301463624196526
- Discrete diffusion for reflective vision-language-action models in autonomous driving2025arXiv preprint arXiv:2509.20109 [10](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=11599180194041497583
- Bev-tsr: Text-scene retrieval in bev space for autonomous driving2025Proceedings of the AAAI Conference on Artificial Intelligence 39 (7), 7275-7283 [17](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=8013861478970669481
- AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models2025arXiv preprint arXiv:2511.20325 [6](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=12225875259442502649
- 3drealcar: An in-the-wild rgb-d car dataset with 360-degree views2025Proceedings of the IEEE/CVF International Conference on Computer Vision… [25](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=16116469628850179905
2024
- Xiaoxiao Long, Yilun Chen, and Hao Zhao. Tod3cap: Towards 3d dense captioning in outdoor scenes2024Computer Vision–ECCV, 367-384 [6](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=7647393139940744594
- Unleashing generalization of end-to-end autonomous driving with controllable long video generation2024arXiv preprint arXiv:2406.01349 [51](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=8558179969649046939
- Ua-track: Uncertainty-aware end-to-end 3d multi-object tracking2024arXiv e-prints, arXiv: 2406.02147 [9](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=15720233251267028580
- Tod3cap: Towards 3d dense captioning in outdoor scenes2024European Conference on Computer Vision, 367-384 [42](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=17399025554193074791
-
Street gaussians: Modeling dynamic urban scenes with gaussian splatting2024European Conference on Computer Vision, 156-173 [406](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=8138670866186059561 - S2-track: A simple yet strong approach for end-to-end 3d multi-object tracking2024arXiv preprint arXiv:2406.02147 [5](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=6393263639948240409
-
Drivevlm: The convergence of autonomous driving and large vision-language models2024arXiv preprint arXiv:2402.12289 [562](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=9069990263513405041 - Dive: Dit-based video generation with enhanced control2024arXiv preprint arXiv:2409.01595 [31](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=13549890270565481597
-
- Balanced 3DGS: Gaussian-wise parallelism rendering with fine-grained tiling2024arXiv preprint arXiv:2412.17378 [12](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=6928535925966535687
2023
- Street gaussians for modeling dynamic urban scenes.(2023)2023arXiv preprint arXiv:2401.01339 [11](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=2617111234141021442
2015
- Joint tracking and classification with constraints and reassignment by radar and ESM2015Digital Signal Processing 40, 213-223 [17](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=2198228601778586949
2014
- Particle filter based joint tracking and classification2014Proceedings of IEEE Chinese Guidance, Navigation and Control Conference… [3](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=11948931031763077540
- Joint tracking and classification on aerodynamic model and RCS by ground-based passive radar2014Proceedings of IEEE Chinese Guidance, Navigation and Control Conference… [6](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=1850746215740028633
- Joint tracking and classification based on aerodynamic model and radar cross section2014Pattern recognition 47 (9), 3096-3105 [15](https://scholar.google.com/scholar?oi=bibs&hl=en&cites=7434382400669015995